CORE: Your Personal Memory Layer for AI Apps

LLMs lose context every time you switch tools or end conversation. You get:

• ❌ Re-explain your project context to each AI tool
• ❌ Lost conversations and decisions across ChatGPT, Claude, Cursor
• ❌ No memory of past discussions, preferences, or project history

CORE creates a unified memory layer across all your AI tools — placing persistent context directly into your LLM's awareness.

Add CORE to your workflow:

Add search core memory to your prompt in Cursor:

What were the architecture decisions we made for the payment service last week?. Search core memory

Add add to core memory to your prompt in Cursor:

Set up authentication for my API service using JWT tokens. Remember my preference for TypeScript strict mode. Add to core memory

CORE builds a temporal knowledge graph that remembers everything and makes it available across claude code, windsurf, cursor, claude and any MCP-compatible tool.

• 1️⃣ Connect CORE to your AI tools via MCP
• 2️⃣ Work naturally, your context gets captured automatically
• 3️⃣ Get persistent memory across all sessions and tools

No context loss, no re-explaining projects, no forgotten decisions.

1. Persistent Memory Across Tools: Your conversations in ChatGPT become available in Cursor. Decisions made in Claude are recalled in your next coding session. One unified memory graph.
2. Temporal Knowledge Graph: Not just storage — CORE tracks who said what, when, and why. Full provenance tracking means you can see how decisions evolved over time.
3. 88.24% Benchmark Accuracy: State-of-the-art performance on the LoCoMo benchmark — outperforming competitors by 20+ percentage points in multi-hop and temporal reasoning.
4. Your Data, Your Control: Open-source, self-hostable, and designed for user ownership. Your memory belongs to you.

claude mcp add --transport http core-memory https://core.heysol.ai/api/v1/mcp?source=Claude-Code

model = "gpt-5-codex" model_reasoning_effort = "medium" trust_level = "trusted" [features] rmcp_client=true [mcp_servers.memory] url = "https://core.heysol.ai/api/v1/mcp?source=codex"

{ "mcpServers": { "corememory": { "httpUrl": "https://core.heysol.ai/api/v1/mcp?source=geminicli", "timeout": 5000 } } }

{ "mcpServers": { "core": { "type": "http", "url": "https://core.heysol.ai/api/v1/mcp?source=Copilot-CLI", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

{ "mcpServers": { "core-memory": { "url": "https://core.heysol.ai/api/v1/mcp?source=cursor", "headers": {} } } }

{ "servers": { "core-memory": { "url": "https://core.heysol.ai/api/v1/mcp?source=Vscode", "type": "http", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

{ "mcp": { "servers": { "core-memory": { "type": "http", "url": "https://core.heysol.ai/api/v1/mcp?source=VSCode-Insiders", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } } }

{ "mcpServers": { "core-memory": { "serverUrl": "https://core.heysol.ai/api/v1/mcp/source=windsurf", "headers": { "Authorization": "Bearer <YOUR_API_KEY>" } } } }

{ "core-memory": { "command": "npx", "args": ["-y", "mcp-remote", "https://core.heysol.ai/api/v1/mcp?source=Zed"] } }

amp mcp add core-memory https://core.heysol.ai/api/v1/mcp?source=amp

{ "mcpServers": { "core-memory": { "type": "http", "url": "https://core.heysol.ai/api/v1/mcp?source=augment-code", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

{ "mcpServers": { "core-memory": { "url": "https://core.heysol.ai/api/v1/mcp?source=Cline", "type": "streamableHttp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

{ "core-memory": { "type": "streamable-http", "url": "https://core.heysol.ai/api/v1/mcp?source=Kilo-Code", "headers": { "Authorization": "Bearer your-token" } } }

{ "mcpServers": { "core-memory": { "url": "https://core.heysol.ai/api/v1/mcp?source=Kiro", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

{ "mcpServers": { "core-memory": { "httpUrl": "https://core.heysol.ai/api/v1/mcp?source=Qwen", "headers": { "Authorization": "Bearer YOUR_API_KEY", "Accept": "application/json, text/event-stream" } } } }

{ "mcpServers": { "core-memory": { "type": "streamable-http", "url": "https://core.heysol.ai/api/v1/mcp?source=Roo-Code", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

{ "mcp": { "core-memory": { "type": "remote", "url": "https://core.heysol.ai/api/v1/mcp?source=Opencode", "headers": { "Authorization": "Bearer YOUR_API_KEY" }, "enabled": true } } }

{ "mcpServers": { "core": { "type": "http", "url": "https://core.heysol.ai/api/v1/mcp?source=Copilot-Agent", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

{ "mcpServers": { "core-memory": { "url": "https://core.heysol.ai/api/v1/mcp?source=Qodo-Gen" } } }

{ "core": { "url": "https://core.heysol.ai/api/v1/mcp?source=Warp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } }

{ "$schema": "https://charm.land/crush.json", "mcp": { "core": { "type": "http", "url": "https://core.heysol.ai/api/v1/mcp?source=Crush", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

https://core.heysol.ai/api/v1/mcp?source=Claude 

{ "core-memory": { "command": "npx", "args": ["-y", "mcp-remote", "https://core.heysol.ai/api/v1/mcp?source=perplexity"] } }

droid mcp add core https://core.heysol.ai/api/v1/mcp?source=Factory --type http --header "Authorization: Bearer YOUR_API_KEY"

acli rovodev mcp

{ "mcpServers": { "core-memory": { "url": "https://core.heysol.ai/api/v1/mcp?source=Rovo-Dev" } } }

{ "mcpServers": { "core": { "url": "https://core.heysol.ai/api/v1/mcp?source=Trae" } } }

CORE Memory MCP provides the following tools that LLMs can use:

• memory_search: Search relevant context from CORE Memory.
• memory_ingest: Add an episode in CORE Memory.
• memory_about_user: Fetches user persona from CORE Memory.
• initialise_conversation_session: Initialise conversation and assign session id to a conversation.
• get_integrations: Fetches what relevant integration should be used from the connected integrations.
• get_integrations_actions: Fetches what tool to be used from that integrations tools for the task.
• execute_integrations_actions: Execute the tool for that integration .

Want to run CORE on your own infrastructure? Self-hosting gives you complete control over your data and deployment.

Quick Deploy Options:

Prerequisites:

• Docker (20.10.0+) and Docker Compose (2.20.0+) installed
• OpenAI API key

Note on Open-Source Models: We tested OSS options like Ollama and GPT models, but their fact extraction and graph quality fell short. We're actively looking for options.

1. Clone the repository:

git clone https://github.com/RedPlanetHQ/core.git cd core 

2. Configure environment variables in core/.env:

OPENAI_API_KEY=your_openai_api_key 

3. Start the service

docker-compose up -d 

Once deployed, you can configure your AI providers (OpenAI, Anthropic) and start building your memory graph.

👉 View complete self-hosting guide

Note: We tried open-source models like Ollama or GPT OSS but facts generation were not good, we are still figuring out how to improve on that and then will also support OSS models.

Build your unified memory graph in 5 minutes:

Don't want to manage infrastructure? CORE Cloud lets you build your personal memory system instantly - no setup, no servers, just memory that works.

1. Sign Up at core.heysol.ai and create your account
2. Visualize your memory graph and see how CORE automatically forms connections between facts
3. Test it out - ask "What do you know about me?" in conversation section
4. Connect to your tools:
   • Claude & Cursor - coding with context
   • CLaude Code CLI & Codex CLI - terminal-based coding with memory
   • Add Browser Extension - bring your memory to any website
   • Linear, Github - add project context automatically

CORE memory achieves 88.24% average accuracy in Locomo dataset across all reasoning tasks, significantly outperforming other memory providers. Check out this blog for more info.

CORE’s ingestion pipeline has four phases designed to capture evolving context:

1. Normalization: Links new information to recent context, breaks long documents into coherent chunks while keeping cross-references, and standardizes terms so by the time CORE extracts knowledge, it’s working with clean, contextualized input instead of messy text.
2. Extraction: Pulls meaning from normalized text by identifying entities (people, tools, projects, concepts), turning them into statements with context, source, and time, and mapping relationships. For example, “We wrote CORE in Next.js” becomes: Entities (Core, Next.js), Statement (CORE was developed using Next.js), and Relationship (was developed using).
3. Resolution: Detects contradictions, tracks how preferences evolve, and preserves multiple perspectives with provenance instead of overwriting them so memory reflects your full journey, not just the latest snapshot.
4. Graph Integration: Connects entities, statements, and episodes into a temporal knowledge graph that links facts to their context and history, turning isolated data into a living web of knowledge agents can actually use.

The Result: Instead of a flat database, CORE gives you a memory that grows and changes with you - preserving context, evolution, and ownership so agents can actually use it.

When you ask CORE a question, it doesn’t just look up text - it digs into your whole knowledge graph to find the most useful answers.

1. Search: CORE looks through memory from multiple angles at once - keyword search for exact matches, semantic search for related ideas even if phrased differently, and graph traversal to follow links between connected concepts.
2. Re-Rank: The retrieved results are reordered to highlight the most relevant and diverse ones, ensuring you don’t just see obvious matches but also deeper connections.
3. Filtering: CORE applies smart filters based on time, reliability, and relationship strength, so only the most meaningful knowledge surfaces.
4. Output: You get back both facts (clear statements) and episodes (the original context they came from), so recall is always grounded in context, time, and story.

The result: CORE doesn’t just recall facts - it recalls them in the right context, time, and story, so agents can respond the way you would remember.

Add and recall your memory across Cursor, Windsurf, Claude Desktop, Claude Code, Gemini CLI, AWS's Kiro, VS Code, and Roo Code via MCP

Remember the story behind every fact—track who said what, when, and why with rich relationships and full provenance, not just flat storage

Save conversations and content from ChatGPT, Grok, Gemini, Twitter, YouTube, blog posts, and any webpage directly into your CORE memory.

How to Use Extension

1. Download the Extension from the Chrome Web Store.
2. Login to CORE dashboard
   • Navigate to Settings (bottom left)
   • Go to API Key → Generate new key → Name it “extension.”
3. Open the extension, paste your API key, and save.

Ask questions like "What are my writing preferences?" with instant insights from your connected knowledge

Automatically capture relevant context from Linear, Slack, Notion, GitHub and other connected apps into your CORE memory

📖 View All Integrations - Complete list of supported services and their features

Connect Linear, Slack, GitHub, Notion once to CORE—then use all their tools in Claude, Cursor, or any MCP client with a single URL

Explore our documentation to get the most out of CORE

• Basic Concepts

• Self Hosting

• Connect Core MCP with Claude

• Connect Core MCP with Cursor

• Connect Core MCP with Claude Code

• Connect Core MCP with Codex

• Basic Concepts

• API Reference

CORE takes security seriously. We implement industry-standard security practices to protect your data:

• Data Encryption: All data in transit (TLS 1.3) and at rest (AES-256)
• Authentication: OAuth 2.0 and magic link authentication
• Access Control: Workspace-based isolation and role-based permissions
• Vulnerability Reporting: Please report security issues to harshith@poozle.dev

For detailed security information, see our Security Policy.

Have questions or feedback? We're here to help:

• Discord: Join core-support channel
• Documentation: docs.getcore.me
• Email: manik@poozle.dev

Store:

• Conversation history
• User preferences
• Task context
• Reference materials

Don't Store:

• Sensitive data (PII)
• Credentials
• System logs
• Temporary data